test_gpu_scripts/scripts/bw1000_smoke.py

47 lines
1.3 KiB
Python

#!/usr/bin/env python3
"""Minimal DTK/PyTorch smoke test used before the full BW1000 suite."""
import json
import torch
try:
import torch_dcu # noqa: F401
except ImportError:
pass
def main() -> None:
count = torch.cuda.device_count()
if not torch.cuda.is_available() or count < 1:
raise SystemExit("DTK PyTorch reports no available accelerator")
devices = []
for index in range(count):
props = torch.cuda.get_device_properties(index)
devices.append({
"index": index,
"name": torch.cuda.get_device_name(index),
"memory_gib": round(props.total_memory / 1024**3, 2),
})
a = torch.randn(2048, 2048, device="cuda:0", dtype=torch.bfloat16)
b = torch.randn(2048, 2048, device="cuda:0", dtype=torch.bfloat16)
c = a @ b
torch.cuda.synchronize()
if not torch.isfinite(c).all().item():
raise SystemExit("BF16 matmul produced non-finite output")
print(json.dumps({
"torch_version": torch.__version__,
"cuda_api_available": torch.cuda.is_available(),
"device_count": count,
"devices": devices,
"bf16_matmul": "PASS",
"checksum": round(float(c.float().mean().item()), 6),
}, indent=2))
if __name__ == "__main__":
main()